Depth Control of a Biomimetic Manta Robot via Reinforcement Learning

Daili Zhang, Guang Pan, Yonghui Cao, Qiaogao Huang, Yong Cao

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

This paper proposes a model-free biomimetic manta robot depth control method based on reinforcement learning. Different from the traditional control method, the reinforcement learning method does not need to establish a mathematical model of the control object, and autonomously learns the control law through data training. Based on the classical Q algorithm, the state space, the action space, and reward function of the depth control of the bionic manta robot are designed. The state-action function is trained offline using the experience replay mechanism and random sampling strategy. Finally, the trained function is transplanted to the biomimetic manta robot prototype to establish a controller. The effectiveness of the proposed control method is verified by experiments.

源语言英语
主期刊名Cognitive Systems and Information Processing - 7th International Conference, ICCSIP 2022, Revised Selected Papers
编辑Fuchun Sun, Angelo Cangelosi, Jianwei Zhang, Yuanlong Yu, Huaping Liu, Bin Fang
出版商Springer Science and Business Media Deutschland GmbH
59-69
页数11
ISBN(印刷版)9789819906161
DOI
出版状态已出版 - 2023
活动7th International Conference on Cognitive Systems and Information Processing, ICCSIP 2022 - Fuzhou, 中国
期限: 17 12月 202218 12月 2022

出版系列

姓名Communications in Computer and Information Science
1787 CCIS
ISSN(印刷版)1865-0929
ISSN(电子版)1865-0937

会议

会议7th International Conference on Cognitive Systems and Information Processing, ICCSIP 2022
国家/地区中国
Fuzhou
时期17/12/2218/12/22

指纹

探究 'Depth Control of a Biomimetic Manta Robot via Reinforcement Learning' 的科研主题。它们共同构成独一无二的指纹。

引用此